Robot Learning Course

Teachers

Giuseppe Averta

giuseppe.averta@polito.it

Assistant Professor at Politecnico di Torino

Office @ Corso Ferrucci 112 Vandal Lab

Francesca Pistilli

francesca.pistilli@polito.it

Assistant Professor at Politecnico di Torino

Office @ Corso Ferrucci 112 Vandal Lab

Andrea Protopapa

andrea.protopapa@polito.it

PhD Candidate at Politecnico di Torino

Office @ Corso Ferrucci 112 Vandal Lab

Davide Buoso

davide.buoso@polito.it

PhD Candidate at Politecnico di Torino

Office @ Corso Ferrucci 112 Vandal Lab

Day	Activity	Time
Monday	Lecture (room 1T)	16:00 - 19:00
Thursday	Lecture (room 6N)	10:00 - 11:30
Friday	Laboratory Session (room 8i)	10:00 - 11:30

Course Modules

Robotics Survival Kit (approx. 10h)

Foundations of sensing and actuation
Kinematics and dynamics of autonomous systems
Motor control
Introduction to ROS programming (optional)
Gaussian Filters, Kalman Filter, Particle Filter (optional)

Intro to Reinforcement Learning

Supervised Learning for Robotics
Imitation Learning vs Reinforcement Learning
Markov Decision Processes

Value-based RL

Planning by Dynamic Programming
Model-Free Prediction
Model-Free Control
Value Function Approximation

Policy Gradients

Finite Difference Policy Gradient
Monte-Carlo Policy Gradient
Actor-Critic approaches
Natural gradient
Deep policy networks

Model-based RL

Model-based learning
Integrated Architectures
Learning and Planning
Real and simulated experience
Monte-Carlo Tree Search
Go use-case

Bandits, Exploration/Exploitation

Intro to bandits
Simple naïve exploration (𝜖-greedy)
Optimistic approaches
Probability matching & Information Value
Multi-armed Bandits
Contextual Bandits

Supervised RL

Behavior cloning
Imitation Learning
Generative IL
Inverse RL

Advanced topics

Sim-to-Real Transfer
Vision and Graph-Based RL
Vision-Language-Action Models
Journal Clubs on relevant research papers

Labs (15h)

Optimal Control
Reward Shaping
Q-Learning (Value-Based RL)
Reinforce, PPO, SAC (Policy Gradients)
Sim-to-Real Policy Transfer

Weekly Lecture Schedule & Materials

Links for slides will work only if you are logged in with your PoliTo credentials. You can find lectures recordings on the university portal approx 1 day after the lecture.

Week	Day	Time	Topic Covered
1	Mon 22/09/25	16:00 - 17:30	L0: Intro to Robot Learning Course
1	Mon 22/09/25	17:30 - 19:00	L1: Foundations of sensing & actuation
1	Thu 25/09/25	10:00 - 11:30	L2a: Kinematics of Robot Manipulators - pt1
2	Mon 29/09/25	16:00 - 17:30	L2a: Kinematics of Robot Manipulators - pt2
2	Mon 29/09/25	17:30 - 19:00	L2b: Dynamics of Robot Manipulators
2	Thu 02/10/25	10:00 - 11:30	L2c: Mobile Robots - pt1
3	Mon 06/10/25	16:00 - 17:30	L2c: Mobile Robots - pt2
3	Mon 06/10/25	17:30 - 19:00	L4a: Intro to ML and DL - pt1
3	Thu 09/10/25	10:00 - 11:30	L4a: Intro to ML and DL - pt2
4	Mon 13/10/25	16:00 - 19:00	L4b: Intro to Reinforcement Learning
4	Thu 16/10/25	10:00 - 11:30	L5a: Markov Decision Processes
5	Mon 20/10/25	16:00 - 19:00	L3 Motor control - pt1 (online)
5	Thu 23/10/25	10:00 - 11:30	L3 Motor control - pt2 (online)
5	Fri 24/10/25	10:00 - 11:30	Lab Session 1: RL Fundamentals
6	Mon 27/10/25	16:00 - 19:00	L5b: Dynamic Programming
6	Thu 30/10/25	10:00 - 11:30	L5c: Model-Free RL -- Prediction and Control
7	Mon 3/11/25	16:00 - 19:00	L5d: Model-Free RL – Value Function Approximation - pt 1
7	Thu 6/11/25	10:00 - 11:30	L5d: Model-Free RL – Value Function Approximation - pt 2
7	Fri 7/11/25	10:00 - 11:30	Lab Session 1: RL Fundamentals
8	Mon 10/11/25	16:00 - 19:00	L6: Policy-based RL - part 1
8	Thu 13/11/25	10:00 - 11:30	Journal Club
8	Fri 14/11/25	10:00 - 11:30	Lab Session 2: Value-based RL (Q-Learning)
9	Mon 17/11/25	16:00 - 19:00	L6: Policy-based RL - part 2
9	Thu 20/11/25	10:00 - 11:30	Journal Club
9	Fri 21/11/25	10:00 - 11:30	Lab Session 2: Value-based RL (Q-Learning)
10	Mon 24/11/25	16:00 - 19:00	L7: Model-based RL
10	Thu 27/11/25	10:00 - 11:30	Journal Club
10	Fri 28/11/25	10:00 - 11:30	Lab Session 3: Policy-based RL
11	Mon 01/12/25	16:00 - 19:00	L8: Bandits & Exploration/Exploitation
11	Thu 04/12/25	10:00 - 11:30	L9: Sim-2-Real transfer
11	Fri 05/12/25	10:00 - 11:30	Lab Session 3: Policy-based RL
12	Mon 08/12/25	16:00 - 19:00	National Holiday
12	Thu 11/12/25	10:00 - 11:30	Journal Club
12	Fri 12/12/25	10:00 - 11:30	Lab Session 4: Sim2Real
13	Mon 15/12/25	16:00 - 19:00	L10: Imitation & Inverse RL
13	Thu 19/12/25	10:00 - 11:30	Journal Club
13	Fri 20/12/25	10:00 - 11:30	Lab Session 4: Sim2Real
14	Mon 22/12/25	16:00 - 19:00	Journal Club
14	Thu 25/12/25	10:00 - 11:30	Winter break
14	Fri 26/12/25	10:00 - 11:30	Winter break
15	Mon 05/01/26	16:00 - 19:00	Winter break
15	Thu 08/01/26	10:00 - 11:30	L11: final lecture on research topics
15	Fri 09/01/26	10:00 - 11:30	Lab Session 4: Sim2Real

Robot Learning Course

Course Description

Link to this page

Teachers

Giuseppe Averta

Francesca Pistilli

Andrea Protopapa

Davide Buoso

Weekly Course Schedule

Course Modules

Robotics Survival Kit (approx. 10h)

Intro to Reinforcement Learning

Value-based RL

Policy Gradients

Model-based RL

Bandits, Exploration/Exploitation

Supervised RL

Advanced topics

Labs (15h)

Resources & Textbooks

Reinforcement Learning: An Introduction

Deep Learning

Robotics Modelling, Planning and Control

Probabilistic Robotics

Gymnasium

PyTorch

Stable Baselines3

OpenAI Spinning Up

David Silver’s RL Course

Berkeley Deep RL Bootcamp

Berkeley Deep RL Bootcamp Resources

Dopamine

Weekly Lecture Schedule & Materials

Links for slides will work only if you are logged in with your PoliTo credentials. You can find lectures recordings on the university portal approx 1 day after the lecture.